## distribution data preparation ####
library(sp)
library(dismo)
## Loading required package: raster
library(raster)
library(gbm)
## Loaded gbm 2.1.5
library(maptools)
## Checking rgeos availability: FALSE
## Note: when rgeos is not available, polygon geometry computations in maptools depend on gpclib,
## which has a restricted licence. It is disabled by default;
## to enable gpclib, type gpclibPermit()
library(rgdal)
## rgdal: version: 1.4-6, (SVN revision 841)
## Geospatial Data Abstraction Library extensions to R successfully loaded
## Loaded GDAL runtime: GDAL 2.2.3, released 2017/11/20
## Path to GDAL shared files: C:/Users/ich/Documents/R/win-library/3.6/rgdal/gdal
## GDAL binary built with GEOS: TRUE
## Loaded PROJ.4 runtime: Rel. 4.9.3, 15 August 2016, [PJ_VERSION: 493]
## Path to PROJ.4 shared files: C:/Users/ich/Documents/R/win-library/3.6/rgdal/proj
## Linking to sp version: 1.3-1
library(sp)
library(shapefiles)
## Loading required package: foreign
##
## Attaching package: 'shapefiles'
## The following objects are masked from 'package:foreign':
##
## read.dbf, write.dbf
# DATA distribution
vignette('sdm', 'dismo')
distribution_shape <- read.shp("C:/Users/ich/Desktop/UNI/räumliche_Vorhersage/distribution_Pakistan_all_test.shp")
distribution_dataframe <- as.data.frame(distribution_shape)
write.csv(distribution_shape, file = "C:/Users/ich/Desktop/UNI/räumliche_Vorhersage/distribution_shape_csv.csv")
occurrence_csv <- paste0(system.file(package="dismo"), "C:/Users/ich/Desktop/UNI/räumliche_Vorhersage/distribution_shape_csv.csv")
head(occurrence_csv)
## [1] "C:/Users/ich/Documents/R/win-library/3.6/dismoC:/Users/ich/Desktop/UNI/räumliche_Vorhersage/distribution_shape_csv.csv"
occurrence <- read.csv("C:/Users/ich/Desktop/UNI/räumliche_Vorhersage/distribution_shape_csv.csv")
head(occurrence)
## X shp.record shp.x shp.y shp.shape.type header.file.code
## 1 1 1 72.07099 35.99492 1 9994
## 2 2 2 71.99009 35.15735 1 9994
## 3 3 3 73.39397 34.45065 1 9994
## 4 4 4 73.16466 33.82338 1 9994
## 5 5 5 73.16823 34.13390 1 9994
## 6 6 6 73.41688 34.00422 1 9994
## header.file.length header.file.version header.shape.type header.xmin
## 1 82230 1000 1 62.23056
## 2 82230 1000 1 62.23056
## 3 82230 1000 1 62.23056
## 4 82230 1000 1 62.23056
## 5 82230 1000 1 62.23056
## 6 82230 1000 1 62.23056
## header.ymin header.xmax header.ymax header.zmin header.zmax header.mmin
## 1 24.13072 77.77783 37.11705 0 0 0
## 2 24.13072 77.77783 37.11705 0 0 0
## 3 24.13072 77.77783 37.11705 0 0 0
## 4 24.13072 77.77783 37.11705 0 0 0
## 5 24.13072 77.77783 37.11705 0 0 0
## 6 24.13072 77.77783 37.11705 0 0 0
## header.mmax
## 1 0
## 2 0
## 3 0
## 4 0
## 5 0
## 6 0
occurrence_lonlat <- occurrence [,3:4]
head(occurrence_lonlat)
## shp.x shp.y
## 1 72.07099 35.99492
## 2 71.99009 35.15735
## 3 73.39397 34.45065
## 4 73.16466 33.82338
## 5 73.16823 34.13390
## 6 73.41688 34.00422
# dataframe distribution data
dataframe_occurrence_record_lonlat <- occurrence [,2:4]
head(dataframe_occurrence_record_lonlat)
## shp.record shp.x shp.y
## 1 1 72.07099 35.99492
## 2 2 71.99009 35.15735
## 3 3 73.39397 34.45065
## 4 4 73.16466 33.82338
## 5 5 73.16823 34.13390
## 6 6 73.41688 34.00422
write.csv(dataframe_occurrence_record_lonlat, "C:/Users/ich/Desktop/UNI/räumliche_Vorhersage/dataframe_occurrence_record_lonlat.csv")
head(dataframe_occurrence_record_lonlat)
## shp.record shp.x shp.y
## 1 1 72.07099 35.99492
## 2 2 71.99009 35.15735
## 3 3 73.39397 34.45065
## 4 4 73.16466 33.82338
## 5 5 73.16823 34.13390
## 6 6 73.41688 34.00422
## species data preparation ####
# read in species_csv
species_subspecies <- read.csv("C:/Users/ich/Desktop/UNI/räumliche_Vorhersage/Pakistan_alles/distribution_Pakistan_all_species.csv")
species_subspecies_cut <- species_subspecies [,0:2]
head(species_subspecies_cut)
## species.C.80 subspecies.C.80
## 1 Actinor_radians
## 2 Actinor_radians
## 3 Actinor_radians
## 4 Aeromachus_stigmatus
## 5 Aeromachus_stigmatus
## 6 Aeromachus_stigmatus
## combine species + distribution + cut (subset) for only 1 species (--> Gegenes_nostrodamus) ####
species_distribution_combined <- data.frame(dataframe_occurrence_record_lonlat, species_subspecies_cut)
head(species_distribution_combined)
## shp.record shp.x shp.y species.C.80 subspecies.C.80
## 1 1 72.07099 35.99492 Actinor_radians
## 2 2 71.99009 35.15735 Actinor_radians
## 3 3 73.39397 34.45065 Actinor_radians
## 4 4 73.16466 33.82338 Aeromachus_stigmatus
## 5 5 73.16823 34.13390 Aeromachus_stigmatus
## 6 6 73.41688 34.00422 Aeromachus_stigmatus
# subset for species: Gegenes_nostrodamus
subset_Gegenes_nostrodamus <- subset(species_distribution_combined, species.C.80=="Gegenes_nostrodamus")
subset_Gegenes_nostrodamus
## shp.record shp.x shp.y species.C.80 subspecies.C.80
## 53 53 74.75619 35.27489 Gegenes_nostrodamus nostrodamus
## 54 54 74.25131 35.28893 Gegenes_nostrodamus nostrodamus
## 55 55 72.38800 35.94713 Gegenes_nostrodamus nostrodamus
## 56 56 71.90671 35.83228 Gegenes_nostrodamus nostrodamus
## 57 57 72.02838 35.21013 Gegenes_nostrodamus nostrodamus
## 58 58 71.88014 34.80043 Gegenes_nostrodamus nostrodamus
## 59 59 71.90288 34.46425 Gegenes_nostrodamus nostrodamus
## 60 60 73.43660 33.89194 Gegenes_nostrodamus nostrodamus
## 61 61 73.09218 34.16677 Gegenes_nostrodamus nostrodamus
## 62 62 72.90301 33.97403 Gegenes_nostrodamus nostrodamus
## 63 63 73.09396 33.89551 Gegenes_nostrodamus nostrodamus
## 64 64 72.61379 33.70444 Gegenes_nostrodamus nostrodamus
## 65 65 72.81188 33.69195 Gegenes_nostrodamus nostrodamus
## 66 66 74.17204 31.62093 Gegenes_nostrodamus nostrodamus
## 67 67 73.99001 31.47994 Gegenes_nostrodamus nostrodamus
## 68 68 66.75859 30.43480 Gegenes_nostrodamus nostrodamus
## 69 69 66.72290 30.06361 Gegenes_nostrodamus nostrodamus
## 70 70 67.00843 24.94896 Gegenes_nostrodamus nostrodamus
## 71 71 73.06086 33.49902 Gegenes_nostrodamus karsana
subset_Gegenes_nostrodamus_lat_lon <- subset_Gegenes_nostrodamus[,2:3]
subset_Gegenes_nostrodamus_lat_lon
## shp.x shp.y
## 53 74.75619 35.27489
## 54 74.25131 35.28893
## 55 72.38800 35.94713
## 56 71.90671 35.83228
## 57 72.02838 35.21013
## 58 71.88014 34.80043
## 59 71.90288 34.46425
## 60 73.43660 33.89194
## 61 73.09218 34.16677
## 62 72.90301 33.97403
## 63 73.09396 33.89551
## 64 72.61379 33.70444
## 65 72.81188 33.69195
## 66 74.17204 31.62093
## 67 73.99001 31.47994
## 68 66.75859 30.43480
## 69 66.72290 30.06361
## 70 67.00843 24.94896
## 71 73.06086 33.49902
#final presence data
p_a <- 1
final_presence <- cbind(subset_Gegenes_nostrodamus_lat_lon, p_a)
final_presence
## shp.x shp.y p_a
## 53 74.75619 35.27489 1
## 54 74.25131 35.28893 1
## 55 72.38800 35.94713 1
## 56 71.90671 35.83228 1
## 57 72.02838 35.21013 1
## 58 71.88014 34.80043 1
## 59 71.90288 34.46425 1
## 60 73.43660 33.89194 1
## 61 73.09218 34.16677 1
## 62 72.90301 33.97403 1
## 63 73.09396 33.89551 1
## 64 72.61379 33.70444 1
## 65 72.81188 33.69195 1
## 66 74.17204 31.62093 1
## 67 73.99001 31.47994 1
## 68 66.75859 30.43480 1
## 69 66.72290 30.06361 1
## 70 67.00843 24.94896 1
## 71 73.06086 33.49902 1
## chelsa data preparation ####
#merge
merged_chelsa_annual_mean_temp_path <- "C:/Users/ich/Desktop/UNI/räumliche_Vorhersage/Pakistan_alles/chelsa/annual_mean_temperature/"
merged_chelsa_annual_mean_temp_path
## [1] "C:/Users/ich/Desktop/UNI/räumliche_Vorhersage/Pakistan_alles/chelsa/annual_mean_temperature/"
merged_chelsa_annual_mean_temp_files <- list.files("C:/Users/ich/Desktop/UNI/räumliche_Vorhersage/Pakistan_alles/chelsa/annual_mean_temperature/")
merged_chelsa_annual_mean_temp_files
## [1] "CHELSA_temp10_01_1979-2013_V1.2_land.tif"
## [2] "CHELSA_temp10_02_1979-2013_V1.2_land.tif"
## [3] "CHELSA_temp10_03_1979-2013_V1.2_land.tif"
## [4] "CHELSA_temp10_04_1979-2013_V1.2_land.tif"
## [5] "CHELSA_temp10_05_1979-2013_V1.2_land.tif"
## [6] "CHELSA_temp10_06_1979-2013_V1.2_land.tif"
## [7] "CHELSA_temp10_07_1979-2013_V1.2_land.tif"
## [8] "CHELSA_temp10_08_1979-2013_V1.2_land (1).tif"
## [9] "CHELSA_temp10_09_1979-2013_V1.2_land.tif"
## [10] "CHELSA_temp10_10_1979-2013_V1.2_land.tif"
## [11] "CHELSA_temp10_11_1979-2013_V1.2_land.tif"
## [12] "CHELSA_temp10_12_1979-2013_V1.2_land.tif"
## [13] "merged"
raster_list <- list(merged_chelsa_annual_mean_temp_files)
raster_list
## [[1]]
## [1] "CHELSA_temp10_01_1979-2013_V1.2_land.tif"
## [2] "CHELSA_temp10_02_1979-2013_V1.2_land.tif"
## [3] "CHELSA_temp10_03_1979-2013_V1.2_land.tif"
## [4] "CHELSA_temp10_04_1979-2013_V1.2_land.tif"
## [5] "CHELSA_temp10_05_1979-2013_V1.2_land.tif"
## [6] "CHELSA_temp10_06_1979-2013_V1.2_land.tif"
## [7] "CHELSA_temp10_07_1979-2013_V1.2_land.tif"
## [8] "CHELSA_temp10_08_1979-2013_V1.2_land (1).tif"
## [9] "CHELSA_temp10_09_1979-2013_V1.2_land.tif"
## [10] "CHELSA_temp10_10_1979-2013_V1.2_land.tif"
## [11] "CHELSA_temp10_11_1979-2013_V1.2_land.tif"
## [12] "CHELSA_temp10_12_1979-2013_V1.2_land.tif"
## [13] "merged"
for(i in 1:12)
{
tilesloop <- paste0(merged_chelsa_annual_mean_temp_path, merged_chelsa_annual_mean_temp_files[i])
tilesloop
raster_list[[i]] <- raster(tilesloop)
rasterliste <- raster_list[[i]]
rasterliste
}
raster_list$filename <- "C:/Users/ich/Desktop/UNI/räumliche_Vorhersage/Pakistan_alles/chelsa/annual_mean_temperature/merged/merged_chelsa_annual_mean_temp.tif"
exporttif <- raster_list$filename
exporttif
## [1] "C:/Users/ich/Desktop/UNI/räumliche_Vorhersage/Pakistan_alles/chelsa/annual_mean_temperature/merged/merged_chelsa_annual_mean_temp.tif"
raster_list$overwrite <- TRUE
all_merged_chelsa_annual_mean_temp_raster <- do.call(raster::merge, raster_list, quote=TRUE)
all_merged_chelsa_annual_mean_temp_raster
## class : RasterLayer
## dimensions : 20880, 43200, 902016000 (nrow, ncol, ncell)
## resolution : 0.008333333, 0.008333333 (x, y)
## extent : -180.0001, 179.9999, -90.00014, 83.99986 (xmin, xmax, ymin, ymax)
## crs : +proj=longlat +datum=WGS84 +no_defs +ellps=WGS84 +towgs84=0,0,0
## source : C:/Users/ich/Desktop/UNI/räumliche_Vorhersage/Pakistan_alles/chelsa/annual_mean_temperature/merged/merged_chelsa_annual_mean_temp.tif
## names : merged_chelsa_annual_mean_temp
## values : -457, 345 (min, max)
plot(all_merged_chelsa_annual_mean_temp_raster, main="all_merged chelsa annual mean temperature")
chelsa_annual_global_prec <-
raster("C:/Users/ich/Desktop/UNI/räumliche_Vorhersage/Pakistan_alles/chelsa/annual_global_prec/CHELSA_bio10_12.tif")
chelsa_prec_warmest_quarter <-
raster("C:/Users/ich/Desktop/UNI/räumliche_Vorhersage/Pakistan_alles/chelsa/prec_warmest_quarter/CHELSA_bio10_18.tif")
chelsa_warmest_quarter_mean_temp <-
raster("C:/Users/ich/Desktop/UNI/räumliche_Vorhersage/Pakistan_alles/chelsa/warmest_quarter_mean_t_global/CHELSA_bio10_10.tif")
plot(all_merged_chelsa_annual_mean_temp_raster, main="all_merged chelsa annual mean temperature")
plot(chelsa_annual_global_prec, main="chelsa annual global prec")
plot(chelsa_prec_warmest_quarter, main="chelsa prec warmest quarter")
plot(chelsa_warmest_quarter_mean_temp, main="chelsa warmest quarter mean temperature")
# crop onto pakistan extent
extend_pakistan <- extent(c(58, 83, 23, 38))
cropped_chelsa_annual_mean_temp_raster <- crop(all_merged_chelsa_annual_mean_temp_raster, extend_pakistan)
cropped_chelsa_annual_mean_temp_raster
## class : RasterLayer
## dimensions : 1800, 3000, 5400000 (nrow, ncol, ncell)
## resolution : 0.008333333, 0.008333333 (x, y)
## extent : 57.99986, 82.99986, 22.99986, 37.99986 (xmin, xmax, ymin, ymax)
## crs : +proj=longlat +datum=WGS84 +no_defs +ellps=WGS84 +towgs84=0,0,0
## source : C:/Users/ich/AppData/Local/Temp/Rtmp6nsTNH/raster/r_tmp_2020-01-19_000355_16336_94256.grd
## names : merged_chelsa_annual_mean_temp
## values : -341, 224 (min, max)
plot(cropped_chelsa_annual_mean_temp_raster)
cropped_chelsa_annual_global_prec <- crop(chelsa_annual_global_prec,extend_pakistan)
cropped_chelsa_annual_global_prec
## class : RasterLayer
## dimensions : 1800, 3000, 5400000 (nrow, ncol, ncell)
## resolution : 0.008333333, 0.008333333 (x, y)
## extent : 57.99986, 82.99986, 22.99986, 37.99986 (xmin, xmax, ymin, ymax)
## crs : +proj=longlat +datum=WGS84 +no_defs +ellps=WGS84 +towgs84=0,0,0
## source : C:/Users/ich/AppData/Local/Temp/Rtmp6nsTNH/raster/r_tmp_2020-01-19_000359_16336_12575.grd
## names : CHELSA_bio10_12
## values : 14, 3406 (min, max)
plot(cropped_chelsa_annual_global_prec)
cropped_chelsa_prec_warmest_quarter <- crop(chelsa_prec_warmest_quarter, extend_pakistan)
cropped_chelsa_prec_warmest_quarter
## class : RasterLayer
## dimensions : 1800, 3000, 5400000 (nrow, ncol, ncell)
## resolution : 0.008333333, 0.008333333 (x, y)
## extent : 57.99986, 82.99986, 22.99986, 37.99986 (xmin, xmax, ymin, ymax)
## crs : +proj=longlat +datum=WGS84 +no_defs +ellps=WGS84 +towgs84=0,0,0
## source : C:/Users/ich/AppData/Local/Temp/Rtmp6nsTNH/raster/r_tmp_2020-01-19_000403_16336_25924.grd
## names : CHELSA_bio10_18
## values : 0, 3221 (min, max)
plot(cropped_chelsa_prec_warmest_quarter)
cropped_chelsa_warmest_quarter_mean_temp <- crop(chelsa_warmest_quarter_mean_temp, extend_pakistan,)
cropped_chelsa_warmest_quarter_mean_temp
## class : RasterLayer
## dimensions : 1800, 3000, 5400000 (nrow, ncol, ncell)
## resolution : 0.008333333, 0.008333333 (x, y)
## extent : 57.99986, 82.99986, 22.99986, 37.99986 (xmin, xmax, ymin, ymax)
## crs : +proj=longlat +datum=WGS84 +no_defs +ellps=WGS84 +towgs84=0,0,0
## source : C:/Users/ich/AppData/Local/Temp/Rtmp6nsTNH/raster/r_tmp_2020-01-19_000407_16336_62071.grd
## names : CHELSA_bio10_10
## values : -110, 402 (min, max)
plot(cropped_chelsa_warmest_quarter_mean_temp)
# rasterstack
rasterstack_pakistan_chelsa <- raster::stack(cropped_chelsa_annual_global_prec,
cropped_chelsa_annual_mean_temp_raster,
cropped_chelsa_prec_warmest_quarter,
cropped_chelsa_warmest_quarter_mean_temp)
rasterstack_pakistan_chelsa
## class : RasterStack
## dimensions : 1800, 3000, 5400000, 4 (nrow, ncol, ncell, nlayers)
## resolution : 0.008333333, 0.008333333 (x, y)
## extent : 57.99986, 82.99986, 22.99986, 37.99986 (xmin, xmax, ymin, ymax)
## crs : +proj=longlat +datum=WGS84 +no_defs +ellps=WGS84 +towgs84=0,0,0
## names : CHELSA_bio10_12, merged_chelsa_annual_mean_temp, CHELSA_bio10_18, CHELSA_bio10_10
## min values : 14, -341, 0, -110
## max values : 3406, 224, 3221, 402
plot(rasterstack_pakistan_chelsa)
# dataframe chelsa
pakistan_chelsa_dataframe <- as.data.frame(rasterstack_pakistan_chelsa)
head(pakistan_chelsa_dataframe)
## CHELSA_bio10_12 merged_chelsa_annual_mean_temp CHELSA_bio10_18
## 1 241 30 22
## 2 229 32 21
## 3 228 29 18
## 4 245 28 18
## 5 281 22 19
## 6 322 9 22
## CHELSA_bio10_10
## 1 286
## 2 288
## 3 285
## 4 283
## 5 277
## 6 263
str(pakistan_chelsa_dataframe)
## 'data.frame': 5400000 obs. of 4 variables:
## $ CHELSA_bio10_12 : int 241 229 228 245 281 322 351 366 372 373 ...
## $ merged_chelsa_annual_mean_temp: int 30 32 29 28 22 9 -5 -9 -14 -16 ...
## $ CHELSA_bio10_18 : int 22 21 18 18 19 22 22 23 23 26 ...
## $ CHELSA_bio10_10 : int 286 288 285 283 277 263 247 243 237 235 ...
## generate pseudo-absence data ####
pseudo_absence_pakistan <- randomPoints(cropped_chelsa_annual_global_prec, 18)
pseudo_absence_pakistan
## x y
## [1,] 63.20403 28.56236
## [2,] 79.57903 26.58736
## [3,] 62.84569 36.02903
## [4,] 82.61236 37.92903
## [5,] 65.31236 37.78736
## [6,] 74.10403 25.46236
## [7,] 75.62069 36.87069
## [8,] 69.55403 30.19569
## [9,] 61.37903 33.82903
## [10,] 71.80403 37.81236
## [11,] 66.93736 30.90403
## [12,] 73.47903 25.32069
## [13,] 73.15403 30.28736
## [14,] 59.04569 32.39569
## [15,] 82.48736 34.08736
## [16,] 59.04569 26.85403
## [17,] 58.32903 26.76236
## [18,] 66.70403 32.13736
head(pseudo_absence_pakistan)
## x y
## [1,] 63.20403 28.56236
## [2,] 79.57903 26.58736
## [3,] 62.84569 36.02903
## [4,] 82.61236 37.92903
## [5,] 65.31236 37.78736
## [6,] 74.10403 25.46236
plot(pseudo_absence_pakistan)
# add column "0" for absence:
p_a <- 0
final_absence <- cbind(pseudo_absence_pakistan, p_a)
final_absence
## x y p_a
## [1,] 63.20403 28.56236 0
## [2,] 79.57903 26.58736 0
## [3,] 62.84569 36.02903 0
## [4,] 82.61236 37.92903 0
## [5,] 65.31236 37.78736 0
## [6,] 74.10403 25.46236 0
## [7,] 75.62069 36.87069 0
## [8,] 69.55403 30.19569 0
## [9,] 61.37903 33.82903 0
## [10,] 71.80403 37.81236 0
## [11,] 66.93736 30.90403 0
## [12,] 73.47903 25.32069 0
## [13,] 73.15403 30.28736 0
## [14,] 59.04569 32.39569 0
## [15,] 82.48736 34.08736 0
## [16,] 59.04569 26.85403 0
## [17,] 58.32903 26.76236 0
## [18,] 66.70403 32.13736 0
# rename latlon columns
final_absence_df <- as.data.frame(final_absence)
final_absence_df
## x y p_a
## 1 63.20403 28.56236 0
## 2 79.57903 26.58736 0
## 3 62.84569 36.02903 0
## 4 82.61236 37.92903 0
## 5 65.31236 37.78736 0
## 6 74.10403 25.46236 0
## 7 75.62069 36.87069 0
## 8 69.55403 30.19569 0
## 9 61.37903 33.82903 0
## 10 71.80403 37.81236 0
## 11 66.93736 30.90403 0
## 12 73.47903 25.32069 0
## 13 73.15403 30.28736 0
## 14 59.04569 32.39569 0
## 15 82.48736 34.08736 0
## 16 59.04569 26.85403 0
## 17 58.32903 26.76236 0
## 18 66.70403 32.13736 0
colnames(final_absence_df)
## [1] "x" "y" "p_a"
names(final_absence_df)[1] <- "shp.x"
names(final_absence_df)[2] <- "shp.y"
final_absence_df
## shp.x shp.y p_a
## 1 63.20403 28.56236 0
## 2 79.57903 26.58736 0
## 3 62.84569 36.02903 0
## 4 82.61236 37.92903 0
## 5 65.31236 37.78736 0
## 6 74.10403 25.46236 0
## 7 75.62069 36.87069 0
## 8 69.55403 30.19569 0
## 9 61.37903 33.82903 0
## 10 71.80403 37.81236 0
## 11 66.93736 30.90403 0
## 12 73.47903 25.32069 0
## 13 73.15403 30.28736 0
## 14 59.04569 32.39569 0
## 15 82.48736 34.08736 0
## 16 59.04569 26.85403 0
## 17 58.32903 26.76236 0
## 18 66.70403 32.13736 0
## combine presence + absence ####
final_p_a_lat_lon <- rbind(final_presence, final_absence_df)
final_p_a_lat_lon
## shp.x shp.y p_a
## 53 74.75619 35.27489 1
## 54 74.25131 35.28893 1
## 55 72.38800 35.94713 1
## 56 71.90671 35.83228 1
## 57 72.02838 35.21013 1
## 58 71.88014 34.80043 1
## 59 71.90288 34.46425 1
## 60 73.43660 33.89194 1
## 61 73.09218 34.16677 1
## 62 72.90301 33.97403 1
## 63 73.09396 33.89551 1
## 64 72.61379 33.70444 1
## 65 72.81188 33.69195 1
## 66 74.17204 31.62093 1
## 67 73.99001 31.47994 1
## 68 66.75859 30.43480 1
## 69 66.72290 30.06361 1
## 70 67.00843 24.94896 1
## 71 73.06086 33.49902 1
## 1 63.20403 28.56236 0
## 2 79.57903 26.58736 0
## 3 62.84569 36.02903 0
## 4 82.61236 37.92903 0
## 5 65.31236 37.78736 0
## 6 74.10403 25.46236 0
## 7 75.62069 36.87069 0
## 8 69.55403 30.19569 0
## 9 61.37903 33.82903 0
## 10 71.80403 37.81236 0
## 11 66.93736 30.90403 0
## 12 73.47903 25.32069 0
## 13 73.15403 30.28736 0
## 14 59.04569 32.39569 0
## 15 82.48736 34.08736 0
## 16 59.04569 26.85403 0
## 17 58.32903 26.76236 0
## 18 66.70403 32.13736 0
## extract rastervalues of chelsa data for whole point data: ####
# only lonlat values for extracting:
final_lat_lon <- final_p_a_lat_lon[,1:2]
final_lat_lon
## shp.x shp.y
## 53 74.75619 35.27489
## 54 74.25131 35.28893
## 55 72.38800 35.94713
## 56 71.90671 35.83228
## 57 72.02838 35.21013
## 58 71.88014 34.80043
## 59 71.90288 34.46425
## 60 73.43660 33.89194
## 61 73.09218 34.16677
## 62 72.90301 33.97403
## 63 73.09396 33.89551
## 64 72.61379 33.70444
## 65 72.81188 33.69195
## 66 74.17204 31.62093
## 67 73.99001 31.47994
## 68 66.75859 30.43480
## 69 66.72290 30.06361
## 70 67.00843 24.94896
## 71 73.06086 33.49902
## 1 63.20403 28.56236
## 2 79.57903 26.58736
## 3 62.84569 36.02903
## 4 82.61236 37.92903
## 5 65.31236 37.78736
## 6 74.10403 25.46236
## 7 75.62069 36.87069
## 8 69.55403 30.19569
## 9 61.37903 33.82903
## 10 71.80403 37.81236
## 11 66.93736 30.90403
## 12 73.47903 25.32069
## 13 73.15403 30.28736
## 14 59.04569 32.39569
## 15 82.48736 34.08736
## 16 59.04569 26.85403
## 17 58.32903 26.76236
## 18 66.70403 32.13736
rasValue_pakistan_all <- extract(rasterstack_pakistan_chelsa, final_lat_lon)
rasValue_pakistan_all
## CHELSA_bio10_12 merged_chelsa_annual_mean_temp CHELSA_bio10_18
## [1,] 674 -138 92
## [2,] 407 -107 68
## [3,] 496 -152 77
## [4,] 639 -120 64
## [5,] 1293 -10 480
## [6,] 1320 37 346
## [7,] 689 102 237
## [8,] 2052 14 881
## [9,] 1726 37 877
## [10,] 1060 100 461
## [11,] 1677 45 768
## [12,] 779 104 102
## [13,] 1060 96 530
## [14,] 589 124 91
## [15,] 518 126 83
## [16,] 212 61 33
## [17,] 154 56 35
## [18,] 203 201 18
## [19,] 916 105 134
## [20,] 42 135 4
## [21,] 856 150 110
## [22,] 313 43 1
## [23,] 30 -66 33
## [24,] 176 45 0
## [25,] 503 151 111
## [26,] 130 -223 53
## [27,] 362 78 161
## [28,] 219 29 0
## [29,] 301 -187 10
## [30,] 338 -3 44
## [31,] 564 165 126
## [32,] 240 132 50
## [33,] 180 28 0
## [34,] 146 -183 124
## [35,] 93 152 8
## [36,] 197 83 6
## [37,] 313 21 10
## CHELSA_bio10_10
## [1,] 91
## [2,] 117
## [3,] 74
## [4,] 103
## [5,] 192
## [6,] 236
## [7,] 299
## [8,] 211
## [9,] 233
## [10,] 297
## [11,] 243
## [12,] 307
## [13,] 297
## [14,] 330
## [15,] 333
## [16,] 302
## [17,] 292
## [18,] 309
## [19,] 305
## [20,] 368
## [21,] 336
## [22,] 293
## [23,] 266
## [24,] 320
## [25,] 316
## [26,] 3
## [27,] 286
## [28,] 282
## [29,] 52
## [30,] 236
## [31,] 326
## [32,] 342
## [33,] 268
## [34,] 47
## [35,] 361
## [36,] 273
## [37,] 286
## final training data ####
pakistan_butterflies_train_final_Gegenes_nostrodamus <- data.frame(final_p_a_lat_lon, rasValue_pakistan_all)
pakistan_butterflies_train_final_Gegenes_nostrodamus
## shp.x shp.y p_a CHELSA_bio10_12 merged_chelsa_annual_mean_temp
## 53 74.75619 35.27489 1 674 -138
## 54 74.25131 35.28893 1 407 -107
## 55 72.38800 35.94713 1 496 -152
## 56 71.90671 35.83228 1 639 -120
## 57 72.02838 35.21013 1 1293 -10
## 58 71.88014 34.80043 1 1320 37
## 59 71.90288 34.46425 1 689 102
## 60 73.43660 33.89194 1 2052 14
## 61 73.09218 34.16677 1 1726 37
## 62 72.90301 33.97403 1 1060 100
## 63 73.09396 33.89551 1 1677 45
## 64 72.61379 33.70444 1 779 104
## 65 72.81188 33.69195 1 1060 96
## 66 74.17204 31.62093 1 589 124
## 67 73.99001 31.47994 1 518 126
## 68 66.75859 30.43480 1 212 61
## 69 66.72290 30.06361 1 154 56
## 70 67.00843 24.94896 1 203 201
## 71 73.06086 33.49902 1 916 105
## 1 63.20403 28.56236 0 42 135
## 2 79.57903 26.58736 0 856 150
## 3 62.84569 36.02903 0 313 43
## 4 82.61236 37.92903 0 30 -66
## 5 65.31236 37.78736 0 176 45
## 6 74.10403 25.46236 0 503 151
## 7 75.62069 36.87069 0 130 -223
## 8 69.55403 30.19569 0 362 78
## 9 61.37903 33.82903 0 219 29
## 10 71.80403 37.81236 0 301 -187
## 11 66.93736 30.90403 0 338 -3
## 12 73.47903 25.32069 0 564 165
## 13 73.15403 30.28736 0 240 132
## 14 59.04569 32.39569 0 180 28
## 15 82.48736 34.08736 0 146 -183
## 16 59.04569 26.85403 0 93 152
## 17 58.32903 26.76236 0 197 83
## 18 66.70403 32.13736 0 313 21
## CHELSA_bio10_18 CHELSA_bio10_10
## 53 92 91
## 54 68 117
## 55 77 74
## 56 64 103
## 57 480 192
## 58 346 236
## 59 237 299
## 60 881 211
## 61 877 233
## 62 461 297
## 63 768 243
## 64 102 307
## 65 530 297
## 66 91 330
## 67 83 333
## 68 33 302
## 69 35 292
## 70 18 309
## 71 134 305
## 1 4 368
## 2 110 336
## 3 1 293
## 4 33 266
## 5 0 320
## 6 111 316
## 7 53 3
## 8 161 286
## 9 0 282
## 10 10 52
## 11 44 236
## 12 126 326
## 13 50 342
## 14 0 268
## 15 124 47
## 16 8 361
## 17 6 273
## 18 10 286